<?xml version="1.0" encoding="utf-8"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:hal="http://hal.archives-ouvertes.fr/" xmlns:gml="http://www.opengis.net/gml/3.3/" xmlns:gmlce="http://www.opengis.net/gml/3.3/ce" version="1.1" xsi:schemaLocation="http://www.tei-c.org/ns/1.0 http://api.archives-ouvertes.fr/documents/aofr-sword.xsd">
  <teiHeader>
    <fileDesc>
      <titleStmt>
        <title>HAL TEI export of hal-04279798</title>
      </titleStmt>
      <publicationStmt>
        <distributor>CCSD</distributor>
        <availability status="restricted">
          <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal</licence>
        </availability>
        <date when="2026-05-17T05:42:47+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Fractional Hitting Sets for Efficient and Lightweight Genomic Data Sketching</title>
            <author role="aut">
              <persName>
                <forename type="first">Timothé</forename>
                <surname>Rouzé</surname>
              </persName>
              <idno type="idhal" notation="numeric">1306342</idno>
              <idno type="halauthorid" notation="string">2949571-1306342</idno>
              <idno type="ORCID">https://orcid.org/0009-0004-2799-6714</idno>
              <affiliation ref="#struct-410272"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Igor</forename>
                <surname>Martayan</surname>
              </persName>
              <email type="md5">781ae90c1a58c5d98e49fe5ff52000fc</email>
              <email type="domain">univ-lille.fr</email>
              <ptr type="url" target="https://igor.martayan.org/"/>
              <idno type="idhal" notation="string">imartayan</idno>
              <idno type="idhal" notation="numeric">1538062</idno>
              <idno type="halauthorid" notation="string">2949572-1538062</idno>
              <idno type="ORCID">https://orcid.org/0009-0008-3007-6168</idno>
              <affiliation ref="#struct-247362"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Camille</forename>
                <surname>Marchet</surname>
              </persName>
              <email type="md5">3fbd206738ae75eb3c313381de849eef</email>
              <email type="domain">univ-lille.fr</email>
              <idno type="idhal" notation="string">camille-marchet</idno>
              <idno type="idhal" notation="numeric">170261</idno>
              <idno type="halauthorid" notation="string">23457-170261</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-7235-7346</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=q07hs7YAAAAJ&amp;hl=fr</idno>
              <affiliation ref="#struct-410272"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Antoine</forename>
                <surname>Limasset</surname>
              </persName>
              <email type="md5">6de70c50e6f0b920c15c07d64a6b83f3</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="string">antoine-limasset</idno>
              <idno type="idhal" notation="numeric">180632</idno>
              <idno type="halauthorid" notation="string">30639-180632</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-0669-4141</idno>
              <idno type="IDREF">https://www.idref.fr/223503908</idno>
              <affiliation ref="#struct-410272"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Camille</forename>
                <surname>MARCHET</surname>
              </persName>
              <email type="md5">3fbd206738ae75eb3c313381de849eef</email>
              <email type="domain">univ-lille.fr</email>
            </editor>
            <funder ref="#projanr-55832"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2023-11-14 14:52:13</date>
              <date type="whenModified">2025-05-05 08:28:43</date>
              <date type="whenReleased">2023-11-15 11:30:36</date>
              <date type="whenProduced">2023-09-03</date>
              <date type="whenEndEmbargoed">2023-11-14</date>
              <ref type="file" target="https://hal.science/hal-04279798v1/document">
                <date notBefore="2023-11-14"/>
              </ref>
              <ref type="file" subtype="greenPublisher" n="1" target="https://hal.science/hal-04279798v1/file/2023.06.21.545875v1.full.pdf" id="file-4284975-3740073">
                <date notBefore="2023-11-14"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="304025">
                <persName>
                  <forename>Camille</forename>
                  <surname>MARCHET</surname>
                </persName>
                <email type="md5">3fbd206738ae75eb3c313381de849eef</email>
                <email type="domain">univ-lille.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04279798</idno>
            <idno type="halUri">https://hal.science/hal-04279798</idno>
            <idno type="halBibtex">rouze:hal-04279798</idno>
            <idno type="halRefHtml">&lt;i&gt;23rd International Workshop on Algorithms in Bioinformatics (WABI 2023&lt;/i&gt;, Sep 2023, Houston, United States. &lt;a target="_blank" href="https://dx.doi.org/10.4230/LIPIcs.WABI.2023.15"&gt;&amp;#x27E8;10.4230/LIPIcs.WABI.2023.15&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">23rd International Workshop on Algorithms in Bioinformatics (WABI 2023, Sep 2023, Houston, United States. &amp;#x27E8;10.4230/LIPIcs.WABI.2023.15&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-4284975-3740073"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="CRISTAL">Centre de Recherche en Informatique, Signal et Automatique de Lille (CRISTAL)</idno>
            <idno type="stamp" n="CRISTAL-BONSAI" corresp="CRISTAL">CRISTAL-BONSAI</idno>
            <idno type="stamp" n="UNIV-RENNES">Université de Rennes</idno>
            <idno type="stamp" n="UNIV-LILLE">Université de Lille</idno>
            <idno type="stamp" n="ANR">ANR</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
            <note type="proceedings" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Fractional Hitting Sets for Efficient and Lightweight Genomic Data Sketching</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Timothé</forename>
                    <surname>Rouzé</surname>
                  </persName>
                  <idno type="idhal" notation="numeric">1306342</idno>
                  <idno type="halauthorid" notation="string">2949571-1306342</idno>
                  <idno type="ORCID">https://orcid.org/0009-0004-2799-6714</idno>
                  <affiliation ref="#struct-410272"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Igor</forename>
                    <surname>Martayan</surname>
                  </persName>
                  <email type="md5">781ae90c1a58c5d98e49fe5ff52000fc</email>
                  <email type="domain">univ-lille.fr</email>
                  <ptr type="url" target="https://igor.martayan.org/"/>
                  <idno type="idhal" notation="string">imartayan</idno>
                  <idno type="idhal" notation="numeric">1538062</idno>
                  <idno type="halauthorid" notation="string">2949572-1538062</idno>
                  <idno type="ORCID">https://orcid.org/0009-0008-3007-6168</idno>
                  <affiliation ref="#struct-247362"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Camille</forename>
                    <surname>Marchet</surname>
                  </persName>
                  <email type="md5">3fbd206738ae75eb3c313381de849eef</email>
                  <email type="domain">univ-lille.fr</email>
                  <idno type="idhal" notation="string">camille-marchet</idno>
                  <idno type="idhal" notation="numeric">170261</idno>
                  <idno type="halauthorid" notation="string">23457-170261</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-7235-7346</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=q07hs7YAAAAJ&amp;hl=fr</idno>
                  <affiliation ref="#struct-410272"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Antoine</forename>
                    <surname>Limasset</surname>
                  </persName>
                  <email type="md5">6de70c50e6f0b920c15c07d64a6b83f3</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="string">antoine-limasset</idno>
                  <idno type="idhal" notation="numeric">180632</idno>
                  <idno type="halauthorid" notation="string">30639-180632</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-0669-4141</idno>
                  <idno type="IDREF">https://www.idref.fr/223503908</idno>
                  <affiliation ref="#struct-410272"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">Leibniz International Proceedings in Informatics</title>
                <meeting>
                  <title>23rd International Workshop on Algorithms in Bioinformatics (WABI 2023</title>
                  <date type="start">2023-09-03</date>
                  <date type="end">2023-09-06</date>
                  <settlement>Houston</settlement>
                  <country key="US">United States</country>
                </meeting>
                <imprint>
                  <date type="datePub">2023-06-24</date>
                </imprint>
              </monogr>
              <idno type="biorxiv">2023.06.21.545875</idno>
              <idno type="doi">10.4230/LIPIcs.WABI.2023.15</idno>
              <relatedItem target="https://doi.org/10.1101/2023.06.21.545875" type="Cites" subtype="http://purl.org/coar/resource_type/c_1843"/>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Sketching</term>
                <term xml:lang="en">Sequence Analysis DNA</term>
                <term xml:lang="en">Jaccard Index</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-bi">Computer Science [cs]/Bioinformatics [q-bio.QM]</classCode>
              <classCode scheme="halTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halOldTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halTreeTypology" n="COMM">Conference papers</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>The exponential increase in publicly available sequencing data and genomic resources necessitates the development of highly efficient methods for data processing and analysis. Locality-sensitive hashing techniques have successfully transformed large datasets into smaller, more manageable sketches while maintaining comparability using metrics such as Jaccard and containment indices. However, fixed-size sketches encounter difficulties when applied to divergent datasets. Scalable sketching methods, such as Sourmash, provide valuable solutions but still lack resourceefficient, tailored indexing. Our objective is to create lighter sketches with comparable results while enhancing efficiency. We introduce the concept of Fractional Hitting Sets, a generalization of Universal Hitting Sets, which uniformly cover a specified fraction of the k -mer space. In theory and practice, we demonstrate the feasibility of achieving such coverage with simple but highly efficient schemes. By encoding the covered k -mers as super- k -mers, we provide a space-efficient exact representation that also enables optimized comparisons. Our novel tool, SuperSampler, implements this scheme, and experimental results with real bacterial collections closely match our theoretical findings. In comparison to Sourmash, SuperSampler achieves similar outcomes while utilizing an order of magnitude less space and memory and operating several times faster. This highlights the potential of our approach in addressing the challenges presented by the ever-expanding landscape of genomic data. SuperSampler is an open-source software and can be accessed at github.com/TimRouze/supersampler . The data required to reproduce the results presented in this manuscript is available at github.com/TimRouze/Expe_SPSP .</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-410272" status="VALID">
          <idno type="IdRef">18388695X</idno>
          <idno type="RNSR">201521249L</idno>
          <idno type="ROR">https://ror.org/05vrs3189</idno>
          <idno type="Wikidata">Q116959497</idno>
          <orgName>Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189</orgName>
          <orgName type="acronym">CRIStAL</orgName>
          <date type="start">2015-01-01</date>
          <desc>
            <address>
              <addrLine>Université de Lille - Campus scientifique - Bâtiment ESPRIT - Avenue Henri Poincaré - 59655 Villeneuve d’Ascq</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.cristal.univ-lille.fr/</ref>
          </desc>
          <listRelation>
            <relation name="UMR9189" active="#struct-120930" type="direct"/>
            <relation name="UMR9189" active="#struct-374570" type="direct"/>
            <relation name="UMR9189" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-247362" status="VALID">
          <idno type="ROR">https://ror.org/03rxtdc22</idno>
          <orgName>École normale supérieure - Rennes</orgName>
          <orgName type="acronym">ENS Rennes</orgName>
          <desc>
            <address>
              <addrLine>Campus de Ker Lann - avenue Robert Schuman - 35170 Bruz</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ens-rennes.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-120930" status="VALID">
          <idno type="IdRef">256304629</idno>
          <idno type="ISNI">0000000122034461</idno>
          <idno type="ROR">https://ror.org/01x441g73</idno>
          <orgName>Centrale Lille</orgName>
          <desc>
            <address>
              <addrLine>École Centrale de Lille - Cité Scientifique - CS 20048 59651 Villeneuve d'Ascq Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://centralelille.fr/</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-374570" status="VALID">
          <idno type="IdRef">223446556</idno>
          <idno type="ISNI">0000 0001 2242 6780</idno>
          <idno type="ROR">https://ror.org/02kzqn938</idno>
          <idno type="Wikidata">Q3551621</idno>
          <orgName>Université de Lille</orgName>
          <desc>
            <address>
              <addrLine>EPE Université de Lille. -- 42 rue Paul Duez, 59000 Lille</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.univ-lille.fr/</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-441569" status="VALID">
          <idno type="IdRef">02636817X</idno>
          <idno type="ISNI">0000000122597504</idno>
          <idno type="ROR">https://ror.org/02feahw73</idno>
          <orgName>Centre National de la Recherche Scientifique</orgName>
          <orgName type="acronym">CNRS</orgName>
          <date type="start">1939-10-19</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.cnrs.fr/</ref>
          </desc>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-55832" status="VALID">
          <idno type="anr">ANR-21-CE45-0012</idno>
          <orgName>Agate</orgName>
          <desc>Structures de graphe adaptées pour l'exploration de données de séquençage de troisième génération</desc>
          <date type="start">2021</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>